From 759429e882a587fef13d560c218b59c563be54b9 Mon Sep 17 00:00:00 2001 From: Daniel Balcells Date: Mon, 3 Mar 2025 16:05:16 -0500 Subject: [PATCH] Format example as quote --- ...n AI Models Predict What Youll Say Next.md | 32 +++++++++---------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/content/research/Can AI Models Predict What Youll Say Next.md b/content/research/Can AI Models Predict What Youll Say Next.md index f45dcef6c..b1a93b6b3 100644 --- a/content/research/Can AI Models Predict What Youll Say Next.md +++ b/content/research/Can AI Models Predict What Youll Say Next.md @@ -42,22 +42,22 @@ We specifically chose to use our internal Discord data because it represents aut Below is an example of the resulting snippets: -#### Context -- Vince: the ultimate test of trust -- Courtland: oh shit, like that could be the eval metric! -you can directly monitor coherence over time by monitoring how your honcho wagers in a prediction market -or how it interacts in a socal sandbox with other agents -this is always running if you want and updating as it learns about you -- Vince: yeah, over-arching idea here is to come up with a plethora of ways to assess the coherence of the psychological renderings to their principals IRL -- Courtland: you could even "train" your honcho by reviewing and rewarding highly cohered actions -- Courtland: exactly, ones that are relevant in practice - -#### Options -Next message from Vince: -- A) I'm thinking we need to establish some baseline metrics first though - like what does 'coherence' even mean in this context? psychological fidelity? -- B) this reminds me of those old Tamagotchi pets, but instead of feeding it you're constantly training it to think like you do. kinda wild when you think about it -- C) yeah and we could even gamify the process, giving users points for when their honcho makes decisions that align with what they would've done -- D) ohh yeah like a more proactive approach as opposed to being bayesian, updating priors based on new information +> #### Context +> - Vince: the ultimate test of trust +> - Courtland: oh shit, like that could be the eval metric! +> you can directly monitor coherence over time by monitoring how your honcho wagers in a prediction market +> or how it interacts in a socal sandbox with other agents +> this is always running if you want and updating as it learns about you +> - Vince: yeah, over-arching idea here is to come up with a plethora of ways to assess the coherence of the psychological renderings to their principals IRL +> - Courtland: you could even "train" your honcho by reviewing and rewarding highly cohered actions +> - Courtland: exactly, ones that are relevant in practice +> +> #### Options +> Next message from Vince: +> - A) I'm thinking we need to establish some baseline metrics first though - like what does 'coherence' even mean in this context? psychological fidelity? +> - B) this reminds me of those old Tamagotchi pets, but instead of feeding it you're constantly training it to think like you do. kinda wild when you think about it +> - C) yeah and we could even gamify the process, giving users points for when their honcho makes decisions that align with what they would've done +> - D) ohh yeah like a more proactive approach as opposed to being bayesian, updating priors based on new information ### Context Modes